Plots
# Load necessary libraries
library(plotly)
## Warning: package 'plotly' was built under R version 4.3.3
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
# Update labels for the 'Mental_Health_Condition' column to be more descriptive
data$Mental_Health_Condition <- factor(data$Mental_Health_Condition,
levels = c("0", "1", "2", "3"),
labels = c("None", "Depression", "Anxiety", "Burnout"))
# Create the base ggplot object
p <- ggplot(data, aes(x = as.factor(Mental_Health_Condition), fill = as.factor(Mental_Health_Condition))) +
# Use geom_bar to create a bar chart
# position_dodge2 is used to avoid overlapping of bars
geom_bar(position = position_dodge2(padding = 0.2)) +
# Set custom colors for bars based on mental health condition
scale_fill_manual(values = c("None" = "#FF7F7F", "Depression" = "#6495ED",
"Anxiety" = "#98FB98", "Burnout" = "#DDA0DD")) +
# Add title and axis labels
labs(title = "Distribution of Mental Health Conditions Across Industries",
x = "Mental Health Condition",
y = "Count",
fill = "Mental Health Condition") +
# Use a minimal theme
theme_minimal() +
# Customize theme elements (title, legend position, remove x-axis text)
theme(plot.title = element_text(face = "bold"),
legend.position = "top",
axis.text.x = element_blank()) +
# Create separate subplots for each industry with independent y-axes
facet_wrap(~ Industry, scales = "free_y")
# Convert the static ggplot object to an interactive plotly object
interactive_plot <- ggplotly(p)
# Display the interactive plot
interactive_plot
# Relationship between Physical Activity, Sleep Quality, and Mental Health Resources
# Create a ggplot object
ggplot(data, aes(x = factor(Physical_Activity), y = factor(Sleep_Quality))) +
# Use geom_count to create a bubble plot where size represents frequency
geom_count(aes(color = factor(Access_to_Mental_Health_Resources)),
position = "jitter") + # Add jitter to avoid overplotting
# Set custom colors for points based on access to mental health resources
scale_color_manual(values = c("0" = "#FF6B6B", "1" = "#4ECDC4"),
labels = c("No Access", "Has Access")) +
# Control the size of the points
scale_size_continuous(range = c(3, 10)) +
# Set labels for the x-axis (Physical Activity)
scale_x_discrete(labels = c("1" = "None", "2" = "Weekly", "3" = "Daily")) +
# Set labels for the y-axis (Sleep Quality)
scale_y_discrete(labels = c("1" = "Poor", "2" = "Average", "3" = "Good")) +
# Add title, subtitle, and axis labels
labs(title = "Physical Activity vs Sleep Quality",
subtitle = "Size indicates frequency, Color indicates access to mental health resources",
x = "Physical Activity Level",
y = "Sleep Quality",
color = "Mental Health Resources",
size = "Count") +
# Use a minimal theme
theme_minimal() +
# Customize theme elements (title, subtitle, legend position)
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
legend.title = element_text(size = 12, face = "bold"),
legend.text = element_text(size = 12),
legend.position = "right",
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 12)
)
# Violin plot showing distribution of Hours Worked by Mental Health Condition
# Create a ggplot object
ggplot(data, aes(x = factor(Mental_Health_Condition), y = Hours_Worked_Per_Week)) +
# Use geom_violin to create a violin plot
geom_violin(fill = "lightblue", alpha = 0.7) + # Set fill color and transparency
# Set labels for the x-axis (Mental Health Condition)
scale_x_discrete(labels = c("0" = "None", "1" = "Depression",
"2" = "Anxiety", "3" = "Burnout")) +
# Add title and axis labels
labs(title = "Distribution of Work Hours by Mental Health Condition",
x = "Mental Health Condition",
y = "Hours Worked Per Week") +
# Use a minimal theme
theme_minimal() +
# Customize theme elements (title)
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
legend.position = "right",
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 12)
)
# Years of Experience & Mental Health Condition - Violin Plot
# Violin plot with split density
ggplot(data, aes(x = factor(Mental_Health_Condition),
y = Years_of_Experience,
fill = factor(Mental_Health_Condition))) +
geom_violin(trim = FALSE, alpha = 0.7) +
geom_jitter(position = position_jitter(width = 0.2),
color = "black",
alpha = 0.4) +
scale_x_discrete(labels = c("0" = "None",
"1" = "Depression",
"2" = "Anxiety",
"3" = "Burnout")) +
scale_fill_manual(values = c("0" = "#E0E0E0",
"1" = "#FF9999",
"2" = "#99CCFF",
"3" = "#FFD580")) +
labs(title = "Years of Experience by Mental Health Condition",
x = "Mental Health Condition",
y = "Years of Experience") +
theme_minimal() +
theme(legend.position = "none")
## Warning: No shared levels found between `names(values)` of the manual scale and the
## data's fill values.
## No shared levels found between `names(values)` of the manual scale and the
## data's fill values.
## No shared levels found between `names(values)` of the manual scale and the
## data's fill values.
# Bar plot of Work-Life Balance Rating distribution
# Create a ggplot object
ggplot(data, aes(x = factor(Work_Life_Balance_Rating, # Convert Work_Life_Balance_Rating to a factor with ordered levels
levels = c("1", "2", "3", "4", "5"),
labels = c("Very Poor", "Poor", "Average", "Good", "Excellent")),
fill = factor(Work_Location))) +
# Use geom_bar to create a bar chart
# position_dodge2 is used to avoid overlapping of bars
geom_bar(position = "dodge2", alpha = 0.85) +
# Set custom colors for bars based on work location
scale_fill_manual(values = c("Hybrid" = "skyblue2", "Onsite" = "darkseagreen4", "Remote" = "plum3")) +
# Set the y-axis limits (Number of Employees)
scale_y_continuous(limits = c(0, 400)) +
# Add title and axis labels
labs(title = "Work-Life Balance Ratings by Work Location",
x = "Work-Life Balance Rating",
y = "Number of Employees",
fill = "Work Location") +
# Use a minimal theme
theme_minimal() +
# Customize theme elements (title, legend position)
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
legend.position = "right",
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 12)
)
library(viridis)
## Warning: package 'viridis' was built under R version 4.3.3
## Loading required package: viridisLite
# Create composite scores and new variables
data <- data %>%
mutate(
# Create a Wellbeing Score (0-10)
Wellbeing_Score = (Work_Life_Balance_Rating + (4 - Stress_Level) +
Sleep_Quality + (4 - Social_Isolation_Rating)) / 4,
# Create an Engagement Score (0-10)
Engagement_Score = (Satisfaction_with_Remote_Work +
Company_Support_for_Remote_Work +
Physical_Activity) / 3,
# Create Experience Categories
Experience_Level = case_when(
Years_of_Experience < 5 ~ "Junior",
Years_of_Experience < 10 ~ "Mid-Level",
Years_of_Experience < 15 ~ "Senior",
TRUE ~ "Expert"
),
# Create Workload Category
Workload_Category = case_when(
Hours_Worked_Per_Week < 35 ~ "Light",
Hours_Worked_Per_Week <= 45 ~ "Normal",
Hours_Worked_Per_Week <= 55 ~ "Heavy",
TRUE ~ "Excessive"
),
# Create Meeting Intensity Score
Meeting_Intensity = Number_of_Virtual_Meetings / Hours_Worked_Per_Week,
# Create Work-Life Balance Category
Balance_Category = case_when(
Work_Life_Balance_Rating <= 2 ~ "Poor",
Work_Life_Balance_Rating <= 3 ~ "Average",
TRUE ~ "Good"
)
)
# Plot 2: Complex Heatmap with Multiple Variables
productivity_matrix <- data %>%
group_by(Experience_Level, Workload_Category) %>%
summarise(
Avg_Productivity = mean(Productivity_Change, na.rm = TRUE),
Stress_Level = mean(Stress_Level, na.rm = TRUE),
Count = n(),
.groups = 'drop'
)
ggplot(productivity_matrix,
aes(x = Experience_Level, y = Workload_Category)) +
geom_tile(aes(fill = Avg_Productivity)) +
geom_text(aes(label = round(Stress_Level, 1)),
color = "white", size = 5) +
geom_text(aes(label = paste("n=", Count)),
color = "white", size = 5, vjust = 2) +
scale_fill_viridis() +
labs(title = "Productivity Matrix",
subtitle = "Numbers show Average Stress Level and Sample Size",
x = "Experience Level",
y = "Workload Category",
fill = "Avg Productivity\nChange") +
theme_minimal()+
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
legend.position = "right",
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 12)
)
# Gender - bar plot
# Gender summary data
gender_summary <- data %>%
count(Gender) %>%
mutate(percentage = n/sum(n) * 100,
# Create labels with both count and percentage
label = sprintf("%d\n(%.2f%%)", n, percentage))
# Create a bar plot
ggplot(gender_summary,
aes(x = reorder(Gender, n), y = n)) +
geom_bar(stat = "identity",aes(fill = Gender),width = 0.6) +
geom_text(aes(label = label),hjust = -0.2, size = 4) +
scale_fill_manual(values = c("Male" = "#4682B4",
"Female" = "#CD6889",
"Non-binary" = "#90EE90",
"Prefer not to say" = "#D3D3D3")) +
coord_flip() +
scale_y_continuous(
expand = expansion(mult = c(0, 0.2))) +
theme_minimal() +
theme(legend.position = "none",
axis.text = element_text(size = 12),
axis.title = element_text(size = 14, face = "bold"),
plot.title = element_text(size = 16, face = "bold"),
plot.subtitle = element_text(size = 11,color = "gray30",margin = margin(b = 10))) +
labs(
title = "Gender Distribution",
subtitle = paste("Total Responses:", sum(gender_summary$n)),
x = NULL,
y = "Number of Responses")
# Mental Health Condition - Pie Chart
# Calculate the counts and percentages
mental_health_summary <- data %>%
count(Mental_Health_Condition) %>%
mutate(
percentage = n / sum(n) * 100,
percentage_label = sprintf("%.1f%%", percentage),
# Create labels combining condition name and percentage
label_position = cumsum(percentage) - (percentage / 2),
)
# Create pie chart
ggplot(mental_health_summary,
aes(x = "", y = percentage, fill = Mental_Health_Condition)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0) +
# Add percentage labels
geom_text(aes(y = label_position,
label = paste0(Mental_Health_Condition, "\n",
percentage_label, "\n",
"(Count=", n, ")")),
color = "black", size = 5) +
scale_fill_brewer(palette = "Set2") +
theme_minimal() +
theme(
axis.title = element_blank(),
axis.text = element_blank(),
panel.grid = element_blank(),
plot.title = element_text(hjust = 0.5, size = 16, face = "bold"),
legend.title = element_text(size = 14, face = "bold"),
legend.text = element_text(size = 12)) +
labs(title = "Mental Health Condition Distribution",
fill = "Condition")
# Create a bar chart to show the distribution of productivity change
ggplot(data, aes(x = factor(Productivity_Change))) +
# Create bars with a skyblue color, and black borders for each category of productivity change
geom_bar(fill = "skyblue2", color ="black") +
# Add title and axis labels
labs(title = "Productivity Change Distribution", # Title of the plot
x = "Productivity Change", # Label for the x-axis
y = "Count") + # Label for the y-axis
# Customize the x-axis labels to show more meaningful text for each productivity change category
scale_x_discrete(labels = c("-1" = "Decrease", # Label for 'Decrease' category
"0" = "No Change", # Label for 'No Change' category
"1" = "Increase")) + # Label for 'Increase' category
# Customize the appearance of the plot
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5), # Title styling with bold font and centered
plot.subtitle = element_text(size = 12, hjust = 0.5), # Subtitle styling (no subtitle in this case)
axis.title = element_text(size = 14, face = "bold"), # Axis titles in bold font
axis.text = element_text(size = 12) # Axis labels with text size 12
)
# Create a stacked bar chart to show the distribution of stress levels across work locations
ggplot(data, aes(x = Work_Location, fill = factor(Stress_Level))) +
# Create the stacked bar chart, using 'fill' to stack the bars proportionally based on stress levels
geom_bar(position = "fill") + # 'position = "fill"' ensures the bars show proportions, not raw counts
# Add titles and axis labels
labs(title = "Stress Level Distribution Across Work Locations", # Title of the plot
x = "Work Location", # Label for x-axis
y = "Proportion") + # Label for y-axis
# Manually define colors for each stress level and set the legend labels
scale_fill_manual(
name = "Stress Level", # Title for the legend
values = RColorBrewer::brewer.pal(3, "Set2"), # Choose a color palette from RColorBrewer for stress levels
labels = c("Low", "Medium", "High") # Set labels for the legend
) +
# Customize the appearance of the plot
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5), # Title styling
plot.subtitle = element_text(size = 12, hjust = 0.5), # Subtitle styling (although no subtitle here)
legend.position = "right", # Position of the legend
axis.title = element_text(size = 14, face = "bold"), # Axis title styling
axis.text = element_text(size = 12), # Axis text styling
legend.title = element_text(size = 14, face = "bold"), # Legend title styling
legend.text = element_text(size = 12) # Legend text styling
)
# Job Role & Satisfaction with Remote Work
satisfaction_heatmap <- data %>%
mutate(Satisfaction_with_Remote_Work = factor(Satisfaction_with_Remote_Work,
levels = c(1, 2, 3),
labels = c("Unsatisfied", "Neutral", "Satisfied"))) %>%
group_by(Job_Role) %>%
summarise(
count = n(),
majority_satisfaction = Satisfaction_with_Remote_Work[which.max(table(Satisfaction_with_Remote_Work))]
) %>%
mutate(Job_Role = reorder(Job_Role, count))
# Plot
ggplot(satisfaction_heatmap, aes(x = Job_Role, y = 1, fill = majority_satisfaction)) +
geom_tile() +
geom_text(aes(label = sprintf("%s\nn=%d", majority_satisfaction, count)),
color = "black", size = 4.5, hjust = 0.5, vjust = 0.5) +
scale_fill_manual(values = c("Unsatisfied" = "#FFB6C1",
"Neutral" = "#FFFF90",
"Satisfied" = "#C1FFC1"),
name = "Satisfaction Level") +
labs(title = "Remote Work Satisfaction by Job Role",
caption = "n:Number of employees",
x = "Job Role", y = NULL) +
theme_minimal() +
theme(
axis.text.y = element_text(size = 10),
axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
legend.position = "right",
plot.title = element_text(face = "bold", size = 16, hjust = 0.5),
axis.title = element_text(size = 14, face = "bold"), # Axis title styling
axis.text = element_text(size = 13), # Axis text styling
) +
coord_flip()
# 4. Stacked Bar Chart: Mental Health Condition by Access to Resources
# Calculate proportions with proper factor conversion
prop_data <- data %>%
mutate(
# Convert Mental Health Condition and Access to Resources to factors for proper handling in the plot
Mental_Health_Condition = factor(Mental_Health_Condition),
Access_to_Mental_Health_Resources = factor(Access_to_Mental_Health_Resources)) %>%
# Group data by Mental Health Condition and count occurrences of Access to Resources within each condition
group_by(Mental_Health_Condition) %>%
count(Access_to_Mental_Health_Resources) %>%
# Calculate the proportion (percentage) of each category within each mental health condition group
mutate(prop = n/sum(n) * 100)
# Create a proportional stacked bar chart
ggplot(prop_data,
aes(x = Mental_Health_Condition, # x-axis represents the mental health conditions
y = prop, # y-axis represents the proportion of individuals
fill = Access_to_Mental_Health_Resources)) + # Fill color is based on access to resources
# Create the bars using the calculated proportions
geom_bar(stat = "identity") +
# Add percentage labels to the bars to show the exact value of the proportions
geom_text(aes(label = sprintf("%.1f%%", prop)), # Format the proportion as a percentage with one decimal point
position = position_stack(vjust = 0.5), # Position labels at the center of each stacked segment
color = "black", # Color of the text
size = 3.5) + # Text size for clarity
# Customize the colors for the "Yes" and "No" categories using a color palette
scale_fill_manual(values = RColorBrewer::brewer.pal(3, "Set2"), # Use a palette of 3 colors for the fill
labels = c("No", "Yes"), # Label the legend
name = "Access to Resources") + # Title for the fill legend
# Add plot title, subtitle, and axis labels
labs(title = "Access to Mental Health Resources by Condition", # Main title of the plot
subtitle = "Showing proportional distribution", # Subtitle for context
x = "Mental Health Condition", # Label for the x-axis
y = "Percentage", # Label for the y-axis
fill = "Access to Resources") + # Label for the legend
# Customize the x-axis labels to represent the different mental health conditions
scale_x_discrete(
labels = c("0" = "None", # Label '0' as 'None' for no mental health condition
"1" = "Depression", # Label '1' as 'Depression'
"2" = "Anxiety", # Label '2' as 'Anxiety'
"3" = "Burnout")) + # Label '3' as 'Burnout'
# Apply a minimal theme for a clean and simple plot appearance
theme_minimal() +
# Customize plot elements such as text alignment, title font, and subtitle font color
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5), # Title styling
legend.position = "right", # Position of the legend
axis.title = element_text(size = 14, face = "bold"), # Axis title styling
axis.text = element_text(size = 12), # Axis text styling
legend.title = element_text(size = 14, face = "bold"), # Legend title styling
legend.text = element_text(size = 12) # Legend text styling
)
# Company Support for Remote Work & Satisfaction with Remote Work
# 1. Stacked Bar Chart
# First, transform the data to aggregate satisfaction levels for each support level
# Group the data by Company Support for Remote Work level
satisfaction_by_support <- data %>%
group_by(Company_Support_for_Remote_Work) %>% # Grouping by support level for remote work
summarise(
# Count the number of employees in each satisfaction level
Satisfied = sum(Satisfaction_with_Remote_Work == 3), # Employees satisfied with remote work (score 3)
Neutral = sum(Satisfaction_with_Remote_Work == 2), # Employees neutral about remote work (score 2)
Unsatisfied = sum(Satisfaction_with_Remote_Work == 1) # Employees unsatisfied with remote work (score 1)
) %>%
# Reshape the data from wide format to long format for stacked bar chart
tidyr::pivot_longer(
cols = c(Satisfied, Neutral, Unsatisfied), # Columns to pivot
names_to = "Satisfaction_Level", # New column for satisfaction levels
values_to = "Count" # New column for the counts of each satisfaction level
)
# Create stacked bar chart
ggplot(satisfaction_by_support,
aes(x = factor(Company_Support_for_Remote_Work), # X-axis: Company support for remote work (categorical)
y = Count, # Y-axis: Count of employees in each satisfaction level
fill = Satisfaction_Level)) + # Fill color based on satisfaction level
# Create stacked bars where each bar represents the total count per support level,
# and different satisfaction levels are stacked on top of each other
geom_bar(stat = "identity", position = "stack") +
# Customize the color scale for satisfaction levels
scale_fill_manual(values = c("Satisfied" = "#4CAF50", # Green for satisfied employees
"Neutral" = "#FFC107", # Yellow for neutral employees
"Unsatisfied" = "#EF5350")) + # Red for unsatisfied employees
# Add titles and labels for the plot
labs(title = "Remote Work Satisfaction by Company Support Level", # Title of the chart
subtitle = "Distribution of satisfaction levels for each support level", # Subtitle for context
x = "Company Support Level", # Label for the x-axis
y = "Number of Employees", # Label for the y-axis
fill = "Satisfaction Level") + # Label for the fill legend
# Apply minimal theme for a clean appearance
theme_minimal() +
# Customize various plot elements (font sizes, title, subtitle, axis titles, legend position)
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5), # Title styling
legend.position = "right", # Position of the legend
axis.title = element_text(size = 14, face = "bold"), # Axis title styling
axis.text = element_text(size = 12), # Axis text styling
legend.title = element_text(size = 14, face = "bold"), # Legend title styling
legend.text = element_text(size = 12) # Legend text styling
)
# Customize x-axis labels to represent different levels of company support for remote work
scale_x_discrete(labels = c("1" = "Very Low Support", # Label for score 1
"2" = "Low Support", # Label for score 2
"3" = "Moderate Support", # Label for score 3
"4" = "High Support", # Label for score 4
"5" = "Very High Support")) # Label for score 5
## <ggproto object: Class ScaleDiscretePosition, ScaleDiscrete, Scale, gg>
## aesthetics: x xmin xmax xend
## axis_order: function
## break_info: function
## break_positions: function
## breaks: waiver
## call: call
## clone: function
## dimension: function
## drop: TRUE
## expand: waiver
## get_breaks: function
## get_breaks_minor: function
## get_labels: function
## get_limits: function
## get_transformation: function
## guide: waiver
## is_discrete: function
## is_empty: function
## labels: Very Low Support Low Support Moderate Support High Suppo ...
## limits: NULL
## make_sec_title: function
## make_title: function
## map: function
## map_df: function
## n.breaks.cache: NULL
## na.translate: TRUE
## na.value: NA
## name: waiver
## palette: function
## palette.cache: NULL
## position: bottom
## range: environment
## range_c: environment
## rescale: function
## reset: function
## train: function
## train_df: function
## transform: function
## transform_df: function
## super: <ggproto object: Class ScaleDiscretePosition, ScaleDiscrete, Scale, gg>
# 2. Trend Line Chart
# Calculate average satisfaction for each support level
satisfaction_trend <- data %>%
group_by(Company_Support_for_Remote_Work) %>%
summarise(
avg_satisfaction = mean(Satisfaction_with_Remote_Work),
sd_satisfaction = sd(Satisfaction_with_Remote_Work),
n = n(),
se = sd_satisfaction / sqrt(n)
)
# Create trend line with confidence interval
ggplot(satisfaction_trend,
aes(x = factor(Company_Support_for_Remote_Work),
y = avg_satisfaction)) +
geom_line(aes(group = 1),
color = "#3B82F6",
size = 1) +
geom_point(size = 3,
color = "#3B82F6") +
geom_errorbar(aes(ymin = avg_satisfaction - se,
ymax = avg_satisfaction + se),
width = 0.2) +
scale_y_continuous(limits = c(1, 3),
breaks = seq(1, 3, 0.5)) +
labs(title = "Average Satisfaction Trend by Company Support",
subtitle = "With standard error bars",
x = "Company Support Level",
y = "Average Satisfaction Score") +
theme_minimal() +
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5), # Title styling
legend.position = "right", # Position of the legend
axis.title = element_text(size = 14, face = "bold"), # Axis title styling
axis.text = element_text(size = 12), # Axis text styling
legend.title = element_text(size = 14, face = "bold"), # Legend title styling
legend.text = element_text(size = 12) # Legend text styling
) +
scale_x_discrete(labels = c("1" = "Very Low Support",
"2" = "Low Support",
"3" = "Moderate Support",
"4" = "High Support",
"5" = "Very High Support"))
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
# 3. Pie Chart for Overall Distribution
# Calculate overall satisfaction distribution
satisfaction_dist <- data %>%
group_by(Satisfaction_with_Remote_Work) %>%
summarise(count = n()) %>%
mutate(
percentage = count / sum(count) * 100,
satisfaction_label = case_when(
Satisfaction_with_Remote_Work == 1 ~ "Unsatisfied",
Satisfaction_with_Remote_Work == 2 ~ "Neutral",
Satisfaction_with_Remote_Work == 3 ~ "Satisfied"
),
label = paste0(satisfaction_label, "\n", round(percentage, 1), "%")
)
# Create pie chart
ggplot(satisfaction_dist,
aes(x = "",
y = count,
fill = satisfaction_label)) +
geom_bar(stat = "identity", width = 1) +
coord_polar("y", start = 0) +
scale_fill_manual(values = c("Satisfied" = "#4CAF50",
"Neutral" = "#FFC107",
"Unsatisfied" = "#EF5350")) +
geom_text(aes(label = label),
position = position_stack(vjust = 0.5)) +
labs(title = "Overall Remote Work Satisfaction Distribution",
fill = "Satisfaction Level") +
theme_minimal() +
theme(
plot.title = element_text(face = "bold", size = 16, hjust = 0.5), # Title styling
legend.position = "right", # Position of the legend
legend.title = element_text(size = 14, face = "bold"), # Legend title styling
legend.text = element_text(size = 12), # Legend text styling
panel.grid = element_blank(),
axis.title = element_blank(),
axis.text = element_blank(),
)
# Region Based Average Productivity
# world data
world <- ne_countries(scale = "medium", returnclass = "sf")
world_regions <- world %>%
mutate(
Region = case_when(
continent == "North America" ~ "North America",
continent == "South America" ~ "South America",
continent == "Europe" ~ "Europe",
continent == "Asia" ~ "Asia",
continent == "Africa" ~ "Africa",
continent == "Oceania" ~ "Oceania",
TRUE ~ "Other"
)
)
# dominant stress level based on regions
# Calculate the dominant stress level (Low, Medium, High) for each region
region_stress <- data %>%
group_by(Region, Stress_Level) %>% # Group data by Region and Stress Level
summarize(n = n(), .groups = "drop") %>% # Count the number of observations
group_by(Region) %>% # Re-group by Region
slice_max(n, with_ties = FALSE) %>% # Select the row with the maximum value of Stress_Level
ungroup() %>%
mutate(
# Map Stress_Level back to categorical labels for visualization
Stress_Category = case_when(
Stress_Level == 1 ~ "Low",
Stress_Level == 2 ~ "Medium",
Stress_Level == 3 ~ "High"
)
)
# Load world map data and join with stress level data
world_data <- world_regions %>% # Retrieve world regions (assuming a dataset "world_regions" exists)
left_join(region_stress, by = "Region") # Merge stress level data with world map data
# Plot the map showing dominant stress levels by region
ggplot(data = world_data) +
geom_sf(aes(fill = as.factor(Stress_Category))) + # Color regions based on dominant stress levels
scale_fill_manual(
values = c("Low" = "#4CAF50", "Medium" = "#FFC107", "High" = "#FF5252"), # Custom colors
na.value = "grey70", # Grey for missing data
name = "Stress Level" # Legend title
) +
coord_sf(crs = "+proj=robin") + # Use Robinson projection for a better world map view
theme_minimal() + # Minimalistic theme for clean visualization
theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
legend.title = element_text(size = 12, face = "bold"),
legend.text = element_text(size = 10),
legend.position = "right"
) +
labs(
title = "Global Stress Levels by Region", # Plot title
subtitle = "Dominant stress level across regions", # Subtitle
caption = "Data based on survey responses" # Source information
)
# Work Location - Donut Chart
# Calculate counts and percentages for each Work_Location category
work_location_summary <- data %>%
count(Work_Location) %>% # Count the number of occurrences
mutate(
percentage = n / sum(n) * 100, # Calculate percentage share
percentage_label = sprintf("%.1f%%", percentage), # Format percentage labels
label_position = cumsum(percentage) - (percentage / 2) # Determine label positions for slices
)
# Create a donut chart to visualize work location distribution
ggplot(work_location_summary,
aes(x = 2, y = percentage, fill = Work_Location)) + # Aesthetics for the chart
geom_bar(stat = "identity", width = 1) + # Create bar segments for the donut
coord_polar("y", start = 0) + # Transform bar chart into a circular donut chart
xlim(0.95, 2.5) + # Adjust x-limits to create the donut hole
# Add labels inside the donut slices with category, percentage, and count
geom_text(aes(y = label_position,
label = paste0(Work_Location, "\n", percentage_label, "\n",
"(Count=", n, ")")),
color = "black", size = 4.5, x = 2) +
# Apply a color palette for the slices
scale_fill_brewer(palette = "Set3") +
# Clean up and format the chart appearance
theme_minimal() +
theme(
axis.title = element_blank(), # Remove axis titles
axis.text = element_blank(), # Remove axis text
panel.grid = element_blank(), # Remove grid lines
plot.title = element_text(hjust = 0.5, size = 16, face = "bold"), # Style the title
legend.title = element_text(size = 12, face = "bold"), # Style legend title
legend.text = element_text(size = 11), # Style legend text
plot.background = element_rect(fill = "white", color = NA) # Set white background
) +
# Add chart title and legend title
labs(
title = "Work Location Distribution",
fill = "Work Location"
)
# Perform data analysis by grouping data by Work Location and Job Role
work_pattern_analysis <- data %>%
group_by(Work_Location, Job_Role) %>%
summarize(
# Calculate average productivity change for each group
Avg_Productivity = mean(Productivity_Change, na.rm = TRUE),
# Calculate average stress level for each group
Avg_Stress = mean(Stress_Level, na.rm = TRUE),
# Calculate average satisfaction with remote work for each group
Avg_Satisfaction = mean(Satisfaction_with_Remote_Work, na.rm = TRUE),
# Count the number of employees in each group
Employee_Count = n(),
# Calculate Efficiency Score based on productivity, stress, and satisfaction
Efficiency_Score = Avg_Productivity * (1 - Avg_Stress/3) * Avg_Satisfaction,
# Convert Efficiency Score to percentage
Efficiency_Percent = Efficiency_Score * 100,
# Drop grouping after summarizing
.groups = 'drop'
)
# Create a bar plot to visualize the Efficiency Score by Job Role and Work Location
ggplot(work_pattern_analysis, aes(x = reorder(Job_Role, Efficiency_Percent),
y = Efficiency_Percent,
fill = Work_Location)) +
# Create a bar chart with customized position and width
geom_bar(stat = "identity",
position = position_dodge(width = 0.9),
width = 0.7) +
# Manually define the colors for each work location
scale_fill_manual(name = "Work Location",
values = c(
"Hybrid" = "#4472C4", # Blue for Hybrid
"Onsite" = "#ED7D31", # Orange for Onsite
"Remote" = "#70AD47" # Green for Remote
)) +
# Add chart labels and axis titles
labs(
title = "Work Pattern Efficiency Score by Job Role and Work Location", # Title of the plot
x = "Job Role", # Label for x-axis
y = "Efficiency Score (%)" # Label for y-axis
) +
# Apply minimal theme for clean aesthetics
theme_minimal() +
theme(
plot.title = element_text(size = 14, face = "bold"), # Style title
axis.text.x = element_text(size = 12), # Style x-axis text
axis.text.y = element_text(size = 12), # Style y-axis text
axis.title = element_text(size = 14, face = "bold"), # Style axis titles
legend.text = element_text(size = 12), # Style legend text
legend.title = element_text(size = 14, face = "bold") # Style legend title
) +
# Add labels inside the bars to show Efficiency Percent
geom_text(aes(label = sprintf("%.1f%%", Efficiency_Percent), # Format percentage for label
# Adjust label position based on whether the value is positive or negative
hjust = ifelse(Efficiency_Percent >= 0, -0.2, 1.2)), # Horizontal adjustment
position = position_dodge(width = 0.9), # Ensure text is properly positioned inside bars
size = 4, # Label text size
color = "black") + # Text color
# Flip the coordinates to make the bars horizontal
coord_flip() +
# Add padding to the x and y axes to ensure that labels are fully visible
scale_x_discrete(expand = expansion(mult = c(0.2, 0.2))) +
scale_y_continuous(expand = expansion(mult = c(0.1, 0.2)))
# Overtime Indicator
# Bar Plot
overtime_summary <- data %>%
count(Overtime_Indicator) %>%
mutate(
Overtime_Status = ifelse(Overtime_Indicator == 1, "Overtime", "No Overtime"),
percentage = n / sum(n) * 100,
label = sprintf("%d\n(%.2f%%)", n, percentage)
)
ggplot(overtime_summary, aes(x = Overtime_Status, y = n, fill = Overtime_Status)) +
geom_bar(stat = "identity", width = 0.5) +
geom_text(aes(label = label), size = 4) +
scale_fill_manual(values = c("Overtime" = "yellowgreen", "No Overtime" = "skyblue")) +
labs(
title = "Overtime Indicator Distribution",
x = "Overtime Status",
y = "Number of Employees"
) +
theme_minimal() +
theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
axis.title = element_text(size = 14, face = "bold"),
axis.text = element_text(size = 10),
legend.position = "none"
)
# Stress Level by Work Location
library(ggplot2)
library(RColorBrewer)
# Create the stacked bar chart with normalized proportions
ggplot(data, aes(x = Work_Location, fill = factor(Stress_Level))) +
geom_bar(position = "fill", color = "black") + # Normalize bars (proportionate stacks)
labs(title = "Stress Level Distribution Across Work Locations",
x = "Work Location",
y = "Proportion") +
scale_fill_manual(
name = "Stress Level",
values = RColorBrewer::brewer.pal(3, "Set2"),
labels = c("Low", "Medium", "High")) +
geom_text(stat = "count",
aes(label = scales::percent(..count../sum(..count..))),
position = position_fill(vjust = 0.5),
size = 4, color = "black") + # Add labels to show proportions
theme_minimal() +
theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
axis.title = element_text(size = 14, face = "bold"),
axis.text.x = element_text(size = 10),
axis.text.y = element_text(size = 10),
legend.title = element_text(size = 12, face = "bold"),
legend.text = element_text(size = 10),
legend.position = "right",
)
## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
# Impact of Stress on Productivity by Job Role and Work Location
# Group the data by Stress Level, Job Role, and Work Location to calculate the average productivity change
data %>%
group_by(Stress_Level, Job_Role, Work_Location) %>% # Grouping by stress level, job role, and work location
summarise(
Avg_Productivity = mean(Productivity_Change, na.rm = TRUE), # Calculate average productivity while handling NA values
.groups = 'drop' # Remove the groupings after summarization
) %>%
mutate(
# Categorize productivity based on the average value
Productivity_Category = case_when(
Avg_Productivity > 0 ~ "Increase", # Positive average productivity
Avg_Productivity == 0 ~ "No Change", # Zero average productivity
Avg_Productivity < 0 ~ "Decrease" # Negative average productivity
),
# Ensure a specific order for the productivity categories
Productivity_Category = factor(
Productivity_Category,
levels = c("Decrease", "No Change", "Increase") # Order the categories for better visual representation
),
# Convert Stress_Level to a factor with readable labels
Stress_Level = factor(
Stress_Level,
levels = c(1, 2, 3), # Mapping stress levels (1 = Low, 2 = Moderate, 3 = High)
labels = c("Low", "Moderate", "High") # Assign labels for clarity
)
) %>%
ggplot(aes(x = Stress_Level, y = Job_Role)) + # Define axes for stress level and job role
# Use geom_tile to create a heatmap-like effect with colored tiles for each combination of stress level and job role
geom_tile(aes(fill = Productivity_Category), color = "white", size = 0.7, alpha = 0.6) + # Tile color represents productivity category
# Create facets for different work locations to compare across them
facet_wrap(~Work_Location, nrow = 1) + # Facet by work location with one row for layout
# Assign custom colors to productivity categories
scale_fill_manual(
values = c(
"Decrease" = "red3", # Red for decrease in productivity
"No Change" = "beige", # Beige for no change in productivity
"Increase" = "green4" # Green for increase in productivity
),
name = "Productivity Change" # Legend title for fill colors
) +
# Add titles and labels
labs(
title = "Productivity Changes Under Different Stress Levels", # Plot title
x = "Stress Level", # X-axis label
y = "Job Role" # Y-axis label
) +
# Apply minimal theme for a clean and professional look
theme_minimal() +
theme(
plot.title = element_text(hjust = 0.5, size = 14, face = "bold"), # Center and bold the title
axis.title = element_text(size = 14, face = "bold"), # Bold axis titles
axis.text.x = element_text(size = 8, face = "bold"), # Smaller, bold text for x-axis labels
axis.text.y = element_text(size = 10), # Larger text for y-axis labels
panel.grid = element_blank(), # Remove gridlines for clarity
strip.text = element_text(size = 12, face = "bold"), # Bold facet labels
legend.title = element_text(size = 14, face = "bold"), # Bold legend title
legend.text = element_text(size = 10) # Set size for legend text
)
# Region Based Average Productivity
region_productivity <- data %>%
group_by(Region) %>%
summarise(Average_Productivity = mean(Productivity_Change, na.rm = TRUE))
data <- data %>%
left_join(region_productivity, by = "Region") %>%
mutate(Region_Normalized_Productivity = Productivity_Change / Average_Productivity)
world <- ne_countries(scale = "medium", returnclass = "sf")
world_regions <- world %>%
mutate(
Region = case_when(
continent == "North America" ~ "North America",
continent == "South America" ~ "South America",
continent == "Europe" ~ "Europe",
continent == "Asia" ~ "Asia",
continent == "Africa" ~ "Africa",
continent == "Oceania" ~ "Oceania",
TRUE ~ "Other"
)
)
# Join the normalized productivity data with the world map
world_data <- world_regions %>%
left_join(data %>%
select(Region, Region_Normalized_Productivity) %>%
distinct(),
by = "Region")
## Warning in sf_column %in% names(g): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1 of `x` matches multiple rows in `y`.
## ℹ Row 9 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
ggplot(data = world_data) +
geom_sf(aes(fill = Region_Normalized_Productivity)) +
scale_fill_gradient2(
high = "#4CAF50", mid = "#FFC107", low = "#FF5252",
midpoint = 1, na.value = "grey70", name = "Normalized Productivity"
) +
coord_sf(crs = "+proj=robin") + # Robinson projection for better global view
theme_minimal() +
theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
plot.subtitle = element_text(size = 12, hjust = 0.5),
legend.position = "right",
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
axis.text = element_blank(),
axis.ticks = element_blank()
) +
labs(
title = "Global Normalized Productivity by Region",
subtitle = "Normalized productivity across regions (Productivity / Regional Average)",
caption = "Data based on survey responses"
)
# Calculate proportions for pie charts
pie_data <- data %>%
group_by(Work_Location, Mental_Health_Condition) %>% # Group by work location and mental health condition
summarise(Count = n(), .groups = "drop") %>% # Count the occurrences of each combination of work location and mental health condition
group_by(Work_Location) %>% # Group by work location again to calculate proportions within each location
mutate(
Proportion = Count / sum(Count), # Calculate the proportion of each mental health condition within each work location
Percentage = scales::percent(Proportion, accuracy = 1), # Convert proportions to percentages for display
Mental_Health_Condition = factor( # Convert mental health condition to a factor with readable labels
Mental_Health_Condition,
labels = c("None", "Depression", "Anxiety", "Burnout")
)
)
# Create pie charts faceted by Work Location
ggplot(pie_data, aes(x = "", y = Proportion, fill = Mental_Health_Condition)) + # Set up pie chart data
geom_col(width = 1, color = "white") + # Use geom_col to create bar-like sections of the pie chart with no borders
geom_text(aes(label = Percentage), position = position_stack(vjust = 0.5), size = 3.5) + # Add percentage labels inside the pie sections
coord_polar(theta = "y") + # Convert the bar chart into a pie chart using polar coordinates
facet_wrap(~Work_Location) + # Create separate pie charts for each work location
scale_fill_brewer(palette = "Set3") + # Apply a color palette for better visualization
labs(
title = "Proportion of Mental Health Conditions by Work Location", # Title for the plot
fill = "Mental Health Condition" # Legend label for the fill color
) +
theme_void() + # Use a void theme to remove axes and gridlines, leaving only the pie chart
theme(
plot.title = element_text(size = 14, face = "bold", hjust = 0.5), # Center-align and bold the title
strip.text = element_text(size = 12, face = "bold"), # Format facet labels
legend.title = element_text(size = 12, face = "bold"), # Format the legend title
legend.text = element_text(size = 10) # Format the legend text
)
library(RColorBrewer)
# dashboard of mental health conditions
# Function to calculate position of labels
calculate_positions <- function(data, group_var) {
data %>%
count(!!sym(group_var), Mental_Health_Condition) %>%
group_by(!!sym(group_var)) %>%
mutate(prop = n/sum(n),
pos = cumsum(prop) - prop/2) %>%
ungroup()
}
# Calculate positions for both plots
work_positions <- calculate_positions(data, "Work_Location")
stress_positions <- calculate_positions(data, "Stress_Level")
# Mental Health by Work Location
p1 <- ggplot(data, aes(x = Work_Location, fill = factor(Mental_Health_Condition))) +
geom_bar(position = "fill") +
geom_text(data = work_positions,
aes(y = pos,
label = scales::percent(prop, accuracy = 1),
group = factor(Mental_Health_Condition)),
color = "black",
size = 3) +
scale_fill_brewer(palette = " RdYlGn",
labels = c("None", "Depression", "Anxiety", "Burnout"),
name = "Condition") +
#scale_y_continuous(labels = scales::percent) +
labs(title = "Mental Health Distribution\nby Work Location",
x = "Work Location",
y = "Proportion") +
theme_minimal() +
theme(
plot.title = element_text(size = 12, face = "bold", hjust = 0.6),
axis.text.x = element_text(size = 8),
axis.text.y = element_text(size = 8),
axis.title = element_text(size = 12, face = "bold"),
legend.text = element_text(size = 9),
legend.title = element_text(size = 11, face = "bold"),
legend.position = "right"
)
## Warning: Unknown palette: " RdYlGn"
# Mental Health by Stress Level
p2 <- ggplot(data, aes(x = factor(Stress_Level), fill = factor(Mental_Health_Condition))) +
geom_bar(position = "fill") +
geom_text(data = stress_positions,
aes(y = pos,
label = scales::percent(prop, accuracy = 1),
group = factor(Mental_Health_Condition)),
color = "black",
size = 3) +
scale_fill_brewer(palette = " RdYlGn",
labels = c("None", "Depression", "Anxiety", "Burnout"),
name = "Condition") +
scale_x_discrete(labels = c("Low", "Medium", "High")) +
#scale_y_continuous(labels = scales::percent) +
labs(title = "Mental Health Distribution\nby Stress Level",
x = "Stress Level",
y = "Proportion") +
theme_minimal() +
theme(
plot.title = element_text(size = 12, face = "bold", hjust = 0.6),
axis.text.x = element_text(size = 8),
axis.text.y = element_text(size = 8),
axis.title = element_text(size = 12, face = "bold"),
legend.text = element_text(size = 9),
legend.title = element_text(size = 11, face = "bold"),
legend.position = "right")
## Warning: Unknown palette: " RdYlGn"
# Arrange the plots side by side
grid.arrange(p1, p2, ncol = 2)
# Advanced Job Role Analysis
job_analysis <- data %>%
group_by(Job_Role) %>%
summarise(
avg_stress = mean(Stress_Level),
avg_satisfaction = mean(Satisfaction_with_Remote_Work),
avg_productivity = mean(Productivity_Change),
total_employees = n()
) %>%
arrange(desc(total_employees))
ggplot(job_analysis, aes(x = reorder(Job_Role, total_employees))) +
geom_point(aes(y = avg_stress, color = "Stress Level"), size = 3) +
geom_point(aes(y = avg_satisfaction, color = "Satisfaction"), size = 3) +
geom_point(aes(y = avg_productivity + 2, color = "Productivity"), size = 3) +
geom_text(aes(y = -0.2, label = total_employees), vjust = 1.5) +
scale_color_manual(values = c("Stress Level" = "red",
"Satisfaction" = "blue",
"Productivity" = "green")) +
coord_flip() +
labs(title = "Comprehensive Job Role Analysis",
subtitle = "Showing average stress, satisfaction, and productivity",
x = "Job Role",
y = "Score",
caption = "Numbers show total employees per role") +
theme_minimal() +
theme(
plot.title = element_text(size = 15, face = "bold"),
plot.subtitle = element_text(size = 11),
axis.text.x = element_text(size = 8),
axis.text.y = element_text(size = 8),
axis.title = element_text(size = 14, face ="bold"))
